smrtinsert's favorites

1.		Exploiting the most prominent AI agent benchmarks (rdi.berkeley.edu)
		581 points by Anon84 3 days ago \| 140 comments
2.		Stanford study reveals AI vision models invent images they never see (arxiv.org)
		49 points by LionTurtle13 15 days ago \| 1 comment
3.		How the AI Bubble Bursts (martinvol.pe)
		372 points by martinvol 15 days ago \| 523 comments
4.		We rewrote JSONata with AI in a day, saved $500k/year (reco.ai)
		276 points by cjlm 19 days ago \| 256 comments
5.		$500 GPU outperforms Claude Sonnet on coding benchmarks (github.com/itigges22)
		489 points by yogthos 19 days ago \| 285 comments
6.		Go hard on agents, not on your filesystem (stanford.edu)
		635 points by mazieres 17 days ago \| 329 comments
7.		Show HN: Feather – a fresh Tcl reimplementation (WASM, Go) (feather-lang.dev)
		31 points by dhamidi 3 months ago \| 5 comments
8.		From zero to a RAG system: successes and failures (andros.dev)
		322 points by andros 21 days ago \| 103 comments
9.		Show HN: Atomic – Self-hosted, semantically-connected personal knowledge base (github.com/kenforthewin)
		152 points by kenforthewin 24 days ago \| 27 comments
10.		MCP server that reduces Claude Code context consumption by 98% (mksg.lu)
		570 points by mksglu 45 days ago \| 107 comments
11.		AGENTS.md outperforms skills in our agent evals (vercel.com)
		524 points by maximedupre 75 days ago \| 196 comments
12.		Everything you need to know about act() in React tests (howtotestfrontend.com)
		15 points by howToTestFE 3 months ago
13.		How we lost communication to entertainment (ploum.net)
		701 points by 8organicbits 3 months ago \| 397 comments
14.		Solving a million-step LLM task with zero errors (arxiv.org)
		222 points by Anon84 4 months ago \| 95 comments
15.		Show HN: RowboatX – open-source Claude Code for everyday automations (github.com/rowboatlabs)
		131 points by segmenta 4 months ago \| 42 comments
16.		The Initial Ideal Customer Profile Worksheet (reifyworks.com)
		89 points by mrbbk 5 months ago \| 11 comments
17.		Production RAG: what I learned from processing 5M+ documents (abdellatif.io)
		551 points by tifa2up 5 months ago \| 114 comments
18.		Show HN: Playwright Skill for Claude Code – Less context than playwright-MCP (github.com/lackeyjb)
		189 points by syntax-sherlock 5 months ago \| 45 comments
19.		Tau² benchmark: How a prompt rewrite boosted GPT-5-mini by 22% (quesma.com)
		197 points by blndrt 6 months ago \| 65 comments
20.		Show HN: Making a cross-platform game in Go using WebRTC Datachannels (pion.ly)
		72 points by valorzard 7 months ago \| 12 comments
21.		Vibe coding as a VC (kevinkuipers.substack.com)
		24 points by DanyWin 7 months ago \| 30 comments
22.		Ask HN: The government of my country blocked VPN access. What should I use?
		1338 points by rickybule 7 months ago \| 732 comments
23.		MCP doesn't need tools, it needs code (pocoo.org)
		228 points by the_mitsuhiko 7 months ago \| 140 comments
24.		Donald Trump Is Elected President (nytimes.com)
		791 points by koolba on Nov 9, 2016 \| 1708 comments
25.		Why is AI so slow to spread? (economist.com)
		73 points by 1vuio0pswjnm7 9 months ago \| 184 comments
26.		Andrew Ng: Building Faster with AI [video] (youtube.com)
		302 points by sandslash 9 months ago \| 96 comments
27.		MCP Specification – version 2025-06-18 changes (modelcontextprotocol.io)
		200 points by owebmaster 10 months ago \| 121 comments
28.		MIT 6.S184: Introduction to Flow Matching and Diffusion Models (csail.mit.edu)
		400 points by __rito__ on March 3, 2025 \| 24 comments
29.		Automated reasoning to remove LLM hallucinations (amazon.com)
		57 points by rustastra on Dec 4, 2024 \| 38 comments
30.		Gilead shot prevents all HIV cases in trial (bloomberg.com)
		873 points by toomuchtodo on June 20, 2024 \| 412 comments
		More